cxl: Avoid double free_irq() for psl,slice interrupts

During an eeh call to cxl_remove can result in double free_irq of
psl,slice interrupts. This can happen if perst_reloads_same_image == 1
and call to cxl_configure_adapter() fails during slot_reset
callback. In such a case we see a kernel oops with following back-trace:

Oops: Kernel access of bad area, sig: 11 [#1]
Call Trace:
  free_irq+0x88/0xd0 (unreliable)
  cxl_unmap_irq+0x20/0x40 [cxl]
  cxl_native_release_psl_irq+0x78/0xd8 [cxl]
  pci_deconfigure_afu+0xac/0x110 [cxl]
  cxl_remove+0x104/0x210 [cxl]
  pci_device_remove+0x6c/0x110
  device_release_driver_internal+0x204/0x2e0
  pci_stop_bus_device+0xa0/0xd0
  pci_stop_and_remove_bus_device+0x28/0x40
  pci_hp_remove_devices+0xb0/0x150
  pci_hp_remove_devices+0x68/0x150
  eeh_handle_normal_event+0x140/0x580
  eeh_handle_event+0x174/0x360
  eeh_event_handler+0x1e8/0x1f0

This patch fixes the issue of double free_irq by checking that
variables that hold the virqs (err_hwirq, serr_hwirq, psl_virq) are
not '0' before un-mapping and resetting these variables to '0' when
they are un-mapped.

Cc: stable@vger.kernel.org
Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 871a2f09c71845b2803bab920618c36de634e4fc..8d6ea9712dbd1830fcdc5d6eecda3d28d69a9376 100644 (file)
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -1302,13 +1302,16 @@ int cxl_native_register_psl_err_irq(struct cxl *adapter)
 
 void cxl_native_release_psl_err_irq(struct cxl *adapter)
 {
-       if (adapter->native->err_virq != irq_find_mapping(NULL, adapter->native->err_hwirq))
+       if (adapter->native->err_virq == 0 ||
+           adapter->native->err_virq !=
+           irq_find_mapping(NULL, adapter->native->err_hwirq))
                return;
 
        cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
        cxl_unmap_irq(adapter->native->err_virq, adapter);
        cxl_ops->release_one_irq(adapter, adapter->native->err_hwirq);
        kfree(adapter->irq_name);
+       adapter->native->err_virq = 0;
 }
 
 int cxl_native_register_serr_irq(struct cxl_afu *afu)
@@ -1346,13 +1349,15 @@ int cxl_native_register_serr_irq(struct cxl_afu *afu)
 
 void cxl_native_release_serr_irq(struct cxl_afu *afu)
 {
-       if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+       if (afu->serr_virq == 0 ||
+           afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
                return;
 
        cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
        cxl_unmap_irq(afu->serr_virq, afu);
        cxl_ops->release_one_irq(afu->adapter, afu->serr_hwirq);
        kfree(afu->err_irq_name);
+       afu->serr_virq = 0;
 }
 
 int cxl_native_register_psl_irq(struct cxl_afu *afu)
@@ -1375,12 +1380,15 @@ int cxl_native_register_psl_irq(struct cxl_afu *afu)
 
 void cxl_native_release_psl_irq(struct cxl_afu *afu)
 {
-       if (afu->native->psl_virq != irq_find_mapping(NULL, afu->native->psl_hwirq))
+       if (afu->native->psl_virq == 0 ||
+           afu->native->psl_virq !=
+           irq_find_mapping(NULL, afu->native->psl_hwirq))
                return;
 
        cxl_unmap_irq(afu->native->psl_virq, afu);
        cxl_ops->release_one_irq(afu->adapter, afu->native->psl_hwirq);
        kfree(afu->psl_irq_name);
+       afu->native->psl_virq = 0;
 }
 
 static void recover_psl_err(struct cxl_afu *afu, u64 errstat)